Although cross-modal unsupervised domain adaptation (UDA) has emerged as an effective means to reduce annotation costs for semantic segmentation, existing approaches often struggle to learn semantically consistent, domain-invariant representations under severe domain shifts. To narrow this representational gap, we develop a new strategy that couples an agglomerative visual foundation model–based encoding paradigm with a Multi-scale Adaptive Fusion Module (MAFM). Specifically, we adopt the visual foundation model C-RADIOv3 as the 2D encoder and tailor its representations for dense prediction while keeping the encoder frozen, which yields robust, high-quality features under varying image resolutions. We further introduce MAFM that builds parallel multi-resolution branches on top of the enhanced 2D features and leverages dynamic large and small-kernel convolutions to broaden the receptive field. After cross-scale alignment, MAFM performs per-location adaptive reweighting to fuse complementary cues, thereby strengthening the joint representation of global semantics and fine-grained boundaries. Experiments across multiple scenarios, including USA → Singapore and A2D2 → SemanticKITTI, demonstrate consistent improvements over strong baselines on the 2D and fusion branches; qualitative visualizations further reveal notably better recognition of small-object classes and sharper semantic boundaries, corroborating the effectiveness of the proposed method.

ABSTRACT Point cloud registration, a core task in 3D computer vision for aligning two point clouds via rotation and translation, underpins critical applications like robotic navigation and 3D reconstruction. Classical methods (e.g., Iterative Closest Point) easily converge to local minima under poor initial alignment. Deep learning–based approaches, while efficient, suffer from high annotation costs for large‐scale data. Existing reinforcement learning (RL)‐based methods rely on simple PointNet feature extractors, which are insensitive to local geometric details and thus yield suboptimal registration precision. To address these challenges, we propose ACT‐Agent: Affinity‐Cross Transformer for point cloud registration via reinforcement learning, a novel method that formulates point cloud registration as an RL Markov decision process for iterative optimisation. We leverage Pointnet and Affinity‐Cross Transformer to extract and enhance expressive salient features and assign adaptive weights to channels based on their relative importance. We use RL to autonomously learn from feedback in the environment, freeing ourselves from dependence on data annotation. Experimental results on ModelNet40 (synthetic data) and ScanObjectNN (real‐world data) demonstrate that our proposed ACT‐Agent achieves higher accuracy, efficiency, and generalisation ability than the state‐of‐the‐art methods of point cloud registration.

Object detection is a fundamental challenge encountered in understanding and analyzing remote sensing images. Many current detection methods struggle to identify objects in remote sensing images due to poor feature saliency, diverse directions, and unique viewing angles of small remote sensing targets. As most remote sensing images are captured through overhead photography, the structural contour features of objects in these images remain relatively stable, such as the cross-shaped structure of the aircraft and the rectangular structure of the vehicle. Therefore, we utilize the physical simulation images as prior knowledge to supplement the invariant structural features of the target, extract the target’s key geometric features through the dynamic matching method, and fuse it with the features extracted by the neural network to detect the remote sensing small target more effectively in this article. We propose a template matching method based on physical simulation images (TMSI) and add it to the modified Darknet-53 (named TMSI-Net) for small target detection. Based on this, we perform specific transformations on existing templates in terms of target scale and direction to achieve better adaptation to the corresponding goals and propose DTMSI-Net with a dynamic template library (Dynamic TMSI-Net). Experiments on several datasets demonstrate that the DTMSI-Net exhibits higher detection accuracy and more stable performance compared with the state-of-the-art methods, 4% and 2.7% higher than the second-ranked model on the VEDAI and NWPU datasets, respectively.

Learning-based multi-view stereo (MVS) is gaining prominence as a method for 3D reconstruction. However, existing methods in the process of feature learning fail to focus on the structural information implied in the scene. This oversight prevents the network from perceiving the geometric properties of the scene and weakens the generalizability of the network. Therefore, we propose a novel framework named Point Feature Relation Network for Multi-view Stereo (PFR-MVSNet), which is composed of a Dynamic Structure Perception (DSP) module, an Adaptive Feature Exploration (AFE) module, and a Point Transformer Block (PTB) module, to solve the problems caused by the oversight. The DSP module first augments the feature of the 3D point cloud from multi-view 2D features, then establishes spatial structure relations within local regions on the point cloud and guides the feature learning of points through the aggregated structure information. After the network has fully learned the intra-region structure features, the AFE module repartitions perception regions with similar features. The point features within the regions are further learned by the PTB module. We evaluate our method on three benchmark datasets: DTU, Tanks & Temples, and ETH3D. The experimental results show that our method achieves superior accuracy of 0.289 mm on the DTU dataset and exhibits more robust generalization on the Tanks & Temples and ETH3D datasets compared with other learning-based MVS methods.